CSE-403 Machine Learning

E-mail: atik@cse.green.edu.bd

🕾 Mob. +8801912961096

Room: A-510 Desk No. : 08

Class Routine – Spring 2026 Semester

Day	08:30-10:00	10:00-11:30	11:30-1:00	Break	1:30-03:00	3:00-4:30
Sat
Sun	CSE 404 231_D1 K-109	CSE 404 231_D1 K-109	CSE 403 231_D1 J-107		Tutor Time	Tutor Time
Mon	Tutor Time	Tutor Time
Tue		GED-103 252_D1 K-102	CSE 403 231_D1 J-105		CSE 404 231_D3 K-101	CSE 404 231_D3 K-101
Wed		GED-103 252_D1 G-101
Fri

Topic Outline

Lecture	Selected Topic	Article	Problems
(1)	Introduction	Class Notes
(2-6)	Supervised Learning (Regression, Classification, Linear Regression, Logistic Regression, Importance of designing effective cost function, convex function, learning parameters and parameter optimization concepts)	Class Notes	Assignment 1
(7-10)	Bayesian Decision Theory (review of probability concepts, uncertainty modeling, likelihood, posterior probability, naive decision rules, sensitivity and specificity)	Class Notes
(11-12)	Parametric and non-parametric Methods for density estimation	Class Notes	Quiz 1
(13-14)	Unsupervised Learning (Association rule, KMeans Clustering, etc.)	Class Notes
	Midterm Exam
(15-15)	Perceptron learning (basic architecture and limitations)	Class Notes	Call for a Group Project
(16-19)	Multilayer Perceptrons (importance of non-linearity, understanding artificial neural network architecture, cost function, understanding multivariate calculus and its role in Neural networks, Stochastic Gradient Descent optimization, hyperparameter tuning)	Class Notes
(20-21)	Introduction to Graphical Models	Class Notes	Quiz 2
(22-25)	Time series modeling/online learning (Markov model, Hidden Markov Models, and their applications, Bayesian Networks)	Class Notes
(26-28)	Reinforcement Learning (Markov decision processes and Q-learning)	Class Notes
(29-30)	Design and Analysis of Machine Learning Experiments	Class Notes
	Final Exam